{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:21:26Z","timestamp":1783488086059,"version":"3.55.0"},"reference-count":38,"publisher":"IOP Publishing","issue":"13","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Guangdong Youth Talent program","award":["2024TQ08A386"],"award-info":[{"award-number":["2024TQ08A386"]}]},{"name":"Ministry of Science and Technology\u2019s key research and development program","award":["2023YFF0723400"],"award-info":[{"award-number":["2023YFF0723400"]}]},{"name":"Shenzhen-Hong Kong Joint Lab on Intelliqence Computational Analysis for Tumor Imaqing","award":["E3G111"],"award-info":[{"award-number":["E3G111"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"crossref","award":["2022365"],"award-info":[{"award-number":["2022365"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>High-resolution 3D microscopy has become a foundational tool in biomedical research by reconstructing vascular and neural networks from subcellular to organ scales, thereby facilitating quantitative analysis of tissue microenvironments, disease progression, and early pathological changes. However, accurately segmenting tubular structure like microvascular and neurite in 3D microscopy remains challenging due to their densely packed, span a wide range of calibers, and branch extremely frequently. These characteristics hinder existing deep learning-based segmentation methods from simultaneously enforcing global connectivity and locally plausible radius profiles, often resulting in fragmented branches, spurious connections, and missing fine terminal processes. In this work, we propose a fully 3D topology-supervised segmentation framework for tubular structure that improves connectivity preservation and morphological consistency. Firstly, we introduce a radius-aware topology that integrates local radius estimates directly into connectivity constraints, so that the network simultaneously enforces correct continuity and physiologically credible thickness. Additionally, we implement adaptive topology-error modulation, which amplifies supervision in regions with significant topological deviations. This mechanism directs the network\u2019s focus toward critical errors (e.g. breaks and misjoins) rather than allowing sparse annotations or class imbalance to dominate optimization. Furthermore, we employ efficient large-receptive-field convolutions to capture long-range directional continuity in volumetric data, effectively recovering low-contrast, distal, thin-caliber terminal branches. We validate the approach on three publicly available modalities\u2014electron microscopy vasculature, optical microscopy vasculature, and fluorescently labeled neuronal fibers\u2014and observe that it preserves global 3D connectivity and avoids implausible radius jumps while maintaining strong voxel-level accuracy. Quantitatively, the proposed method achieves the highest Dice\/clDice scores on SELMA3D (0.8839\/0.9173), Mini-vessel (0.8842\/0.9097), and FISBe (0.7803\/0.8033), outperforming the strongest competing baselines across all three datasets. These results suggest consistent performance across different microscopy settings without requiring organ-specific anatomical priors.<\/jats:p>","DOI":"10.1088\/1361-6560\/ae8216","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T22:55:02Z","timestamp":1782341702000},"page":"135030","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Topology-aware segmentation for tubular structure in 3D microscopy"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6973-7402","authenticated-orcid":true,"given":"Yiwen","family":"Sun","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"},{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Peng","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaye","family":"He","sequence":"additional","affiliation":[{"name":"National Innovation Center for Advanced Medical Devices"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6934-0108","authenticated-orcid":true,"given":"Jing","family":"Cai","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2547-0394","authenticated-orcid":true,"given":"Wenjian","family":"Qin","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"pmbae8216bib1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.3389\/fnana.2015.00142","type":"journal-article","article-title":"Crowdsourcing the creation of image segmentation algorithms for connectomics","volume":"9","author":"Arganda-Carreras","year":"2015","journal-title":"Front. Neuroanatomy"},{"key":"pmbae8216bib2","first-page":"pp 3","type":"book","article-title":"A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI","author":"Byrne","year":"2020"},{"key":"pmbae8216bib3","article-title":"Selma3d challenge: self-supervised learning for 3D light-sheet microscopy image segmentation","author":"Chen","year":"2025","type":"preprint"},{"key":"pmbae8216bib4","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s12021-011-9121-2","type":"journal-article","article-title":"Automated tracing of neurites from light microscopy stacks of images","volume":"9","author":"Chothani","year":"2011","journal-title":"Neuroinformatics"},{"key":"pmbae8216bib5","doi-asserted-by":"publisher","first-page":"8766","DOI":"10.1109\/TPAMI.2020.3013679","type":"journal-article","article-title":"A topological loss function for deep-learning based image segmentation using persistent homology","volume":"44","author":"Clough","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbae8216bib6","doi-asserted-by":"publisher","first-page":"e68","DOI":"10.1002\/cpcy.68","type":"journal-article","article-title":"Confocal microscopy: principles and modern practices","volume":"92","author":"Elliott","year":"2020","journal-title":"Curr. Protocols Cytometry"},{"key":"pmbae8216bib7","first-page":"pp 272","type":"book","article-title":"Swin unetr: swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2021"},{"key":"pmbae8216bib8","first-page":"pp 488","type":"conference-proceedings","article-title":"nnu-net revisited: a call for rigorous validation in 3d medical image segmentation","author":"Isensee","year":"2024"},{"key":"pmbae8216bib9","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/s41592-018-0049-4","type":"journal-article","article-title":"High-precision automated reconstruction of neurons with flood-filling networks","volume":"15","author":"Januszewski","year":"2018","journal-title":"Nat. Methods"},{"key":"pmbae8216bib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102485","type":"journal-article","article-title":"NURBS curve shape prior-guided multiscale attention network for automatic segmentation of the inferior alveolar nerve","volume":"120","author":"Jiang","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbae8216bib11","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","type":"journal-article","article-title":"Reducing the hausdorff distance in medical image segmentation with convolutional neural networks","volume":"39","author":"Karimi","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae8216bib12","first-page":"pp 462","type":"conference-proceedings","article-title":"Building skeleton models via 3-D medial surface axis thinning algorithms","volume":"vol 56","author":"Lee","year":"1994"},{"key":"pmbae8216bib13","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1007\/s11548-024-03182-3","type":"journal-article","article-title":"Heart and great vessels segmentation in congenital heart disease via CNN and conditioned energy function postprocessing","volume":"19","author":"Liu","year":"2024","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"pmbae8216bib14","article-title":"U-mamba: enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","type":"preprint"},{"key":"pmbae8216bib15","first-page":"pp 22249","type":"conference-proceedings","article-title":"Fisbe: a real-world benchmark dataset for instance segmentation of long-range thin filamentous structures","author":"Mais","year":"2024"},{"key":"pmbae8216bib16","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1016\/j.jmva.2006.11.013","type":"journal-article","article-title":"Comparing clusterings\u2014an information based distance","volume":"98","author":"Meil\u0103","year":"2007","journal-title":"J. Multivariate Anal."},{"key":"pmbae8216bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2023.108007","type":"journal-article","article-title":"3D imaging and morphometric descriptors of vascular networks on optically cleared organs","volume":"26","author":"Nicolas","year":"2023","journal-title":"iScience"},{"key":"pmbae8216bib18","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/s43586-022-00131-9","type":"journal-article","article-title":"Volume electron microscopy","volume":"2","author":"Peddie","year":"2022","journal-title":"Nat. Rev. Methods Primers"},{"key":"pmbae8216bib19","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1109\/JBHI.2025.3596007","type":"journal-article","article-title":"Utadc-net: unsupervised topological-aware diffusion condensation network for medical image segmentation","volume":"30","author":"Peng","year":"2026","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbae8216bib20","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s41597-023-02048-8","type":"journal-article","article-title":"A dataset of rodent cerebrovasculature from in vivo multiphoton fluorescence microscopy imaging","volume":"10","author":"Poon","year":"2023","journal-title":"Sci. Data"},{"key":"pmbae8216bib21","first-page":"pp 16555","type":"conference-proceedings","article-title":"cldice-a novel topology-preserving loss function for tubular structure segmentation","author":"Shit","year":"2020"},{"key":"pmbae8216bib22","first-page":"pp 16560","type":"conference-proceedings","article-title":"cldice-a novel topology-preserving loss function for tubular structure segmentation","author":"Shit","year":"2021"},{"key":"pmbae8216bib23","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1038\/s43586-021-00069-4","type":"journal-article","article-title":"Light sheet fluorescence microscopy","volume":"1","author":"Stelzer","year":"2021","journal-title":"Nat. Rev. Methods Primers"},{"key":"pmbae8216bib24","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.patrec.2026.02.016","type":"journal-article","article-title":"Za-net: a universal zero-annotation nuclei segmentation network for pathology images via vision-language pre-trained model","volume":"203","author":"Sun","year":"2026","journal-title":"Pattern Recognit. Lett."},{"key":"pmbae8216bib25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1146\/annurev.bioeng.10.061807.160521","type":"journal-article","article-title":"Patient-specific modeling of cardiovascular mechanics","volume":"11","author":"Taylor","year":"2009","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"pmbae8216bib26","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1038\/s41592-020-0792-1","type":"journal-article","article-title":"Machine learning analysis of whole mouse brain vasculature","volume":"17","author":"Todorov","year":"2020","journal-title":"Nat. Methods"},{"key":"pmbae8216bib27","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1109\/TPAMI.2016.2519025","type":"journal-article","article-title":"Reconstructing curvilinear networks using path classifiers and integer programming","volume":"38","author":"T\u00fcretken","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbae8216bib28","doi-asserted-by":"publisher","first-page":"17599","DOI":"10.1109\/TNNLS.2025.3586694","type":"journal-article","article-title":"Sam-med3d: a vision foundation model for general-purpose segmentation on volumetric medical images","volume":"36","author":"Wang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"pmbae8216bib29","first-page":"pp 15682","type":"conference-proceedings","article-title":"Denver: deformable neural vessel representations for unsupervised video vessel segmentation","author":"Wu","year":"2025"},{"key":"pmbae8216bib30","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s11265-008-0217-3","type":"journal-article","article-title":"Retinal vessel radius estimation and a vessel center line segmentation method based on ridge descriptors","volume":"55","author":"Wu","year":"2009","journal-title":"J. Signal Process. Syst."},{"key":"pmbae8216bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2024.101025","type":"journal-article","article-title":"Liver vessel MRI image segmentation based on dual-path diffusion model","volume":"17","author":"Wu","year":"2024","journal-title":"J. Radiat. Res. Appl. Sci."},{"key":"pmbae8216bib32","first-page":"pp 131","type":"book","article-title":"Shape-aware diffusion model for tumor segmentation on Gd-EOB-DTPA MRI images of hepatocellular carcinoma","author":"Wu","year":"2023"},{"key":"pmbae8216bib33","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1093\/bioinformatics\/btt170","type":"journal-article","article-title":"App2: automatic tracing of 3D neuron morphology based on hierarchical pruning of a gray-weighted image distance-tree","volume":"29","author":"Xiao","year":"2013","journal-title":"Bioinformatics"},{"key":"pmbae8216bib34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106356","type":"journal-article","article-title":"G2ViT: graph neural network-guided vision transformer enhanced network for retinal vessel and coronary angiograph segmentation","volume":"176","author":"Xu","year":"2024","journal-title":"Neural Netw."},{"key":"pmbae8216bib35","doi-asserted-by":"publisher","first-page":"9081","DOI":"10.1038\/srep09081","type":"journal-article","article-title":"Soax: a software for quantification of 3D biopolymer networks","volume":"5","author":"Xu","year":"2015","journal-title":"Sci. Rep."},{"key":"pmbae8216bib36","article-title":"Benchmarking the cow with the topcow challenge: topology-aware anatomical segmentation of the circle of willis for cta and mra","author":"Yang","year":"2025","type":"preprint"},{"key":"pmbae8216bib37","doi-asserted-by":"publisher","first-page":"2498","DOI":"10.1364\/BOE.516541","type":"journal-article","article-title":"Deep learning-based vessel extraction in 3D confocal microscope images of cleared human glioma tissues","volume":"15","author":"Yang","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"pmbae8216bib38","first-page":"pp 30896","type":"conference-proceedings","article-title":"Deformcl: learning deformable centerline representation for vessel extraction in 3D medical image","author":"Zhao","year":"2025"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:06:10Z","timestamp":1783487170000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae8216"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":38,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7,8]]},"published-print":{"date-parts":[[2026,7,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae8216","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]},"assertion":[{"value":"Topology-aware segmentation for tubular structure in 3D microscopy","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-01-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}